Abstract

Sequential decision making is a fundamental task faced by any intelligent agent in an extended interaction with its environment; it is the act of answering the question "What should I do now?" In this thesis, I show how to answer this question when "now" is one of a finite set of states, "do" is one of a finite set of actions, "should" is maximize a long-run measure of reward, and "I" is an automated planning or learning system (agent). In particular,

Citations

8881	D.S.: Computers and Intractability, A Guide to the Theory of NP-Completeness - Garey, Johnson - 1979
7321	Introduction to Algorithms - Cormen, Leiserson, et al. - 2001
1964	Dynamic Programming - Bellman - 1957
1950	Computational Complexity - Papadimitriou - 1995
1555	STRIPS: A new approach to the application of theorem proving to problem solving - Fikes, Nilsson - 1971
1446	A new approach to linear filtering and prediction problems - Kalman - 1960
1232	Theory of Linear and Integer Programming - Schrijver - 1986
1135	Learning from delayed rewards - Watkins - 1989
1134	Reinforcement learning: A survey - Kaelbling, Littman, et al. - 1996
1060	Learning to predict by the methods of temporal differences - Sutton - 1988
693	Matrix multiplication via arithmetic progressions - Coppersmith, Winograd - 1990
689	O: Theory of games and economic behavior - Neumann, Morgenstern - 1947
638	Linear Programming and Extensions - Dantzig - 1963
629	Planning and acting in partially observable stochastic domains - Kaelbling, Littman, et al. - 1998
573	A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains - Baum, Petrie, et al. - 1970
545	Some Studies in Machine Learning using the Game of Checkers - Samuel - 2000
539	A new polynomial-time algorithm for linear programming - Karmarkar - 1984
477	Tsitsiklis. Parallel and Distributed Computation: Numerical Methods - Bertsekas, N - 1989
472	Learning to act using real-time dynamic programming - Barto, Bradtke, et al. - 1995
434	Dynamic programming and Markov processes - Howard - 1960
427	Integrated architectures for learning, planning, and reacting based on approximating integrated architectures for learning, planning, and reacting based on approximating dynamic programming - Sutton - 1990
420	A stochastic approximation method - Robbins, Monro - 1951
417	Markov games as a framework for multi-agent reinforcement learning - Littman - 1994
342	Dynamic Programming and Optimal Control, Athena Scientific - Bertsekas - 2000
331	Dynamic Programming: Deterministic and Stochastic Models - Bertsekas - 1987
330	Temporal Difference Learning and TDGammon - Tesauro - 1995
306	Universal plans for reactive robots in unpredictable environments - Schoppers - 1987
285	The Optimal Control of Partially Observable Markov Processes - Sondik - 1971
275	Prioritized sweeping: Reinforcement learning with less data and less time - Moore, Atkeson - 1993
253	The complexity of Markov decision processes - Papadimitriou, Tsisiklis - 1987
243	Acting optimally in partially observable stochastic domains - Cassandra, Kaelbling, et al. - 1994
243	Reinforcement Learning with Selective Perception and Hidden State - McCallum - 1996
235	An algorithm for probabilistic planning - Kushmerick, Hanks, et al. - 1995
235	The optimal control of partially observable Markov processes over a finite horizon - Smallwood, Sondik - 1973
231	Probabilistic robot navigation in partially observable environments - Simmons, Koenig - 1995
223	Generalization in reinforcement learning: safely approximating the value function - Boyan, Moore - 1995
219	Temporal Credit Assignment in Reinforcement Learning - Sutton - 1984
207	Residual Algorithms: Reinforcement Learning with Function Approximation - Baird - 1995
203	The parti-game algorithm for variable resolution reinforcement learning in multidimensional state-spaces - Moore, Atkeson - 1995
202	Learning policies for partially observable environments: Scaling up - Littman, Cassandra, et al.
200	Exploiting structure in policy construction - Boutilier, Dearden, et al. - 1995
195	Interactions between learning and evolution - Ackley, Littman - 1992
192	Probabilistic planning with information gathering and contingent execution - Draper, Hanks, et al. - 1994
186	On the convergence of stochastic iterative dynamic programming algorithms - Jaakkola, Jordan, et al. - 1994
185	Learning and sequential decision making - Barto, Sutton - 1990
185	NP is as easy as detecting unique solutions - Valiant, Vazirani - 1986
173	Reinforcement learning with perceptual aliasing: The perceptual distinctions approach - Chrisman - 1992
172	Stable function approximation in dynamic programming - Gordon - 1995
165	Packet routing in dynamically changing networks: a reinforcement learning approach - Boyan, Littman - 1994
165	Survey of partially observable markov decision processes: Theory, models, and algorithms - Monahan - 1982